Underground water monitoring and early warning method and system based on multi-source data fusion

Abstract

The invention relates to the technical field of environment monitoring, in particular to an underground water monitoring and early warning method and system based on multi-source data fusion, and the method comprises the following steps: obtaining water quality, flow velocity, temperature and pH value data, adjusting the collection frequency, verifying the state of a sensor, forming a water quality and geologic feature data set, analyzing rainfall, air temperature, permeability and water flow dynamic state, and obtaining a water quality and geologic feature data set. And generating a seepage trend, identifying a pollutant diffusion path, range and main path, evaluating a diffusion rate and influence, and generating a pollution diffusion early warning level in combination with permeability and risk standards. According to the invention, through fusion analysis of multi-source data, determination of the correlation between an underground water flowing mode and water quality change, timely capturing of the influence of meteorological change on underground water, accurate evaluation of pollutant diffusion path, rate and influence range, improvement of timeliness and accuracy of pollution early warning, and improvement of monitoring response speed through automatic data processing. And timely and accurate decision support is provided for groundwater resource management and pollution control.

Description

Technical Field

[0001] The present invention relates to the technical field of environmental monitoring, and particularly to a groundwater monitoring and early warning method and system based on multi-source data fusion. Background Art

[0002] The technical field of environmental monitoring includes the monitoring, analysis, evaluation, and early warning of environmental changes to achieve effective management and protection of environmental quality. In this field, groundwater monitoring is an important part, mainly focusing on the quality, quantity, and changes of groundwater resources. Groundwater monitoring technology aims to timely detect problems such as groundwater pollution and overexploitation by collecting and analyzing various data of groundwater, so as to take corresponding management measures. This technical field involves various monitoring means, including sensor technology, data acquisition technology, data transmission technology, and data analysis technology, etc. With the continuous progress of technology, automated and intelligent groundwater monitoring systems have gradually become the research focus, especially how to efficiently and accurately fuse multiple data sources to improve the reliability and real-time performance of the monitoring and early warning system.

[0003] Among them, the groundwater monitoring and early warning method based on multi-source data fusion refers to integrating monitoring data from multiple sources, conducting data fusion analysis, and thus realizing real-time monitoring and early warning of groundwater quality and quantity. This patented method specifically involves obtaining data from different monitoring points, different sensors, and different monitoring technologies, combining multi-source information such as groundwater flow, pollutant concentration, and meteorological data, and comprehensively analyzing the dynamic changes of groundwater. By effectively fusing different data sources, this method constructs a unified monitoring and early warning system to achieve comprehensive monitoring of the state of groundwater resources. Through synchronous processing and optimized analysis of data, this method can more accurately predict the change trend of groundwater, thus providing a scientific basis for groundwater management.

[0004] The existing technologies mainly rely on single or local data sources in groundwater monitoring, and cannot achieve comprehensive monitoring of complex environmental changes. These traditional methods usually lack real-time integration and analysis of multi-dimensional data, and it is difficult to obtain various data such as water quality, flow velocity, and temperature simultaneously. For the functional requirements of monitoring points, the adjustment of data collection frequency also lacks flexibility, which restricts the timeliness and accuracy of data. Existing systems also cannot fully consider different meteorological factors, such as the comprehensive impact of precipitation and temperature changes on groundwater flow patterns and seepage trends. Therefore, in the face of complex meteorological conditions, they cannot accurately predict the dynamic changes of groundwater. The identification of pollutant diffusion paths by traditional methods is relatively rough, and it is impossible to accurately evaluate the diffusion rate and influence range of pollutants, resulting in a slow warning response, unable to identify the pollution source and diffusion range in a timely manner, and affecting the effect of pollution control. Such deficiencies lead to the lack of sufficient accuracy and response speed of existing technologies in dealing with groundwater pollution and resource changes, and it is difficult to provide accurate early warnings and decision-making support. Summary of the Invention

[0005] The purpose of the present invention is to solve the shortcomings existing in the prior art, and a groundwater monitoring and early warning method and system based on multi-source data fusion are proposed.

[0006] In order to achieve the above purpose, the present invention adopts the following technical solutions: A groundwater monitoring and early warning method based on multi-source data fusion, including the following steps:

[0007] S1: Obtain the real-time data of water quality, flow velocity, temperature, and pH value sensors in the monitoring area, adjust the collection frequency according to functional requirements, check and adjust the working state of the sensors, and form a water quality and geological feature data set;

[0008] S2: Call the water quality and geological data set, extract the aquifer thickness and flow direction azimuth angle, analyze the soil permeability and water flow dynamics in combination with precipitation and temperature, identify the impact of meteorological condition changes on groundwater flow patterns, and generate real-time seepage trend results;

[0009] S3: Based on the real-time seepage trend results, extract the seepage direction and flow direction azimuth angle, analyze the pollutant diffusion path, identify the pollutant diffusion range and main path, and generate the pollutant diffusion main path results;

[0010] S4: According to the pollutant diffusion main path results, analyze the changes in pollutant concentration and water flow velocity, identify the diffusion characteristics and permeability effects, and judge the diffusion rate and influence range, and generate the evaluation results of pollutant diffusion trends;

[0011] S5: Combine the pollutant diffusion trend evaluation results, through the analysis of the diffusion path and permeability, and based on the set risk warning criteria, evaluate the severity of pollution diffusion, and generate the pollution diffusion warning level results.

[0012] As a further solution of the present invention, the water quality and geological feature data set includes water quality data, flow velocity data, temperature data, pH value data, sensor status, acquisition frequency adjustment, and monitoring point distribution. The real-time seepage trend result includes soil permeability, groundwater flow pattern, precipitation, air temperature change, seepage trend, and factors associated with water quality change. The main path result of pollutant diffusion includes changes in seepage direction, flow azimuth angle, pollutant concentration change, diffusion path, diffusion range, main diffusion path, and diffusion direction. The pollutant diffusion trend evaluation result includes pollutant concentration change, flow velocity data, diffusion characteristics, diffusion path points, diffusion rate, and influence range. The pollution diffusion warning level result includes pollution diffusion path, permeability characteristics, risk warning standard, severity of pollution diffusion, and warning level.

[0013] As a further solution of the present invention, the specific steps of S1 are as follows:

[0014] S101: Obtain the real-time data of sensors in the monitoring area, compare the data acquisition frequency according to the functional requirements of the monitoring points, and establish a data acquisition frequency offset value;

[0015] S102: Based on the data acquisition frequency offset value, call the spatial distribution coordinates, detect the difference in offset values between adjacent monitoring points, mark the monitoring points that exceed the spatial distribution difference threshold, and generate the abnormal distribution quantity of monitoring points;

[0016] S103: According to the abnormal distribution quantity of the monitoring points, screen the working state parameters of the abnormal monitoring points, adjust the status of the monitoring points below the signal efficiency threshold, and obtain the water quality and geological feature data set.

[0017] As a further solution of the present invention, the specific steps of S2 are as follows:

[0018] S201: Call the water quality and geological feature data set, extract the parameters of aquifer thickness and flow azimuth angle, combine the real-time precipitation and air temperature data, calculate the difference values between the aquifer thickness and flow azimuth angle and precipitation, air temperature, and establish an aquifer dynamic change value;

[0019] S202: Based on the aquifer dynamic change value, call the real-time precipitation and air temperature data, extract the change amplitudes of precipitation and air temperature, and compare the permeability parameters and water flow direction parameters with the change amplitudes of precipitation and air temperature according to the change amplitudes of precipitation and air temperature. Screen the monitoring points with a difference amplitude exceeding the seepage change threshold, and generate a seepage change trend associated with meteorological conditions;

[0020] S203: Correlate the seepage change trend according to the meteorological conditions, extract the turbidity value and conductivity value in the water quality parameters of the monitoring points, judge the correlation between the seepage change trend and the water quality parameter change trend of the corresponding monitoring points, extract the data of the monitoring points with correlation, and obtain the real-time seepage trend result.

[0021] As a further solution of the present invention, the specific steps of S3 are as follows:

[0022] S301: Based on the real-time seepage trend result, extract the seepage direction change parameter and the flow direction azimuth data, compare the two parameters according to the spatial coordinates of the monitoring points, and establish the seepage direction change value;

[0023] S302: According to the seepage direction change value, call the pollutant concentration data, extract the change range of the pollutant concentration at the monitoring points, compare and process according to the change range of the concentration and the seepage direction change, screen the monitoring points where the change range of the concentration exceeds the pollutant concentration change threshold and the corresponding seepage direction change value is greater than the flow direction change reference value, and generate the pollutant diffusion trend interval;

[0024] S303: Based on the pollutant diffusion trend interval, extract the spatial distribution coordinates and flow direction azimuth data of the monitoring points, calculate the pollutant diffusion path direction continuity index according to the spatial coordinates of the monitoring points and the change parameters of the diffusion trend interval, screen the paths with the direction continuity coefficient greater than the path recognition threshold, and obtain the pollutant diffusion main path result.

[0025] As a further solution of the present invention, the specific formula for calculating the pollutant diffusion path direction continuity index is as follows:

[0026]

[0027] Among them, C d represents the pollutant diffusion path direction continuity index, θ i represents the flow direction azimuth data of the i-th monitoring point, X i represents the X coordinate value of the spatial distribution coordinates of the i-th monitoring point, Y i represents the Y coordinate value of the spatial distribution coordinates of the i-th monitoring point, D i represents the change parameter of the diffusion trend interval of the i-th monitoring point, and n represents the total number of monitoring points in the path.

[0028] As a further solution of the present invention, the specific steps of S4 are as follows:

[0029] S401: According to the pollutant diffusion main path result, extract the pollutant concentration change parameter and water flow velocity data of the path points, compare according to the spatial coordinates of the path points and the pollutant concentration change parameter, and establish the pollutant diffusion value of the path points;

[0030] S402: Based on the pollutant diffusion value of the path point, call the path point permeability parameter and water flow velocity data, calculate the diffusion rate index between the path point permeability parameter and the water flow velocity, compare according to the diffusion rate coefficient and the change range of the pollutant concentration at the path point, screen the path points where both the diffusion rate coefficient and the change range of the concentration exceed the diffusion rate reference value, and generate the diffusion rate change trend;

[0031] S403: According to the diffusion rate change trend, extract the spatial distribution coordinates of the path point, judge the coverage range of the diffusion trend based on the diffusion rate change trend and spatial coordinates of the path point, and establish the pollutant diffusion trend evaluation result.

[0032] As a further solution of the present invention, the calculation formula of the path point diffusion rate index value is specifically:

[0033]

[0034] Among them, R e represents the path point diffusion rate index value, K k represents the permeability parameter of the k-th path point, S k represents the water flow velocity data of the k-th path point, C k represents the change range of the pollutant concentration at the k-th path point, represents the average value of the change range of the pollutant concentration at the path point, and M represents the number of path points.

[0035] As a further solution of the present invention, the specific steps of S5 are:

[0036] S501: Based on the pollutant diffusion trend evaluation result, extract the pollutant diffusion path parameter and permeability characteristic data, compare the path points according to the path parameter and permeability characteristic, and establish the path point diffusion characteristic value;

[0037] S502: According to the path point diffusion characteristic value, call the set risk warning standard, extract the change range of the pollutant concentration and the diffusion rate data in the path point diffusion characteristic value, compare according to the change range of the pollutant concentration and the diffusion rate with the threshold value of the risk warning standard, judge the path point diffusion risk, and generate the path point risk level value;

[0038] S503: Based on the path point risk level value, extract all the spatial coordinate data of the path points, calculate the spatial distribution density of the path points with the risk level according to the spatial coordinates and the risk level value, judge whether the distribution density exceeds the risk warning threshold, and establish the pollution diffusion warning level result.

[0039] A groundwater monitoring and early warning system based on multi-source data fusion, comprising:

[0040] The sensing data acquisition module obtains the data of water quality sensors, flow velocity sensors, temperature sensors and pH value sensors deployed in the monitoring area, adjusts the data acquisition frequency according to the functional requirements of the monitoring points, verifies the working status of the sensors according to the spatial distribution of the sensors and adjusts the abnormal data acquisition parameters, and establishes a data set of water quality and geological characteristics;

[0041] The characteristic parameter extraction module calls the data set of water quality and geological characteristics, extracts the aquifer thickness parameter and the flow direction azimuth parameter of the monitoring point, collects the real-time precipitation data and air temperature data in the monitoring area, compares the change range of the aquifer thickness parameter according to the real-time precipitation data, identifies the influence of precipitation and temperature changes on the aquifer thickness, and establishes a real-time seepage trend result;

[0042] Based on the real-time seepage trend result, the seepage trend analysis module obtains the seepage direction change value and the flow direction azimuth parameter of the monitoring point, collects the pollutant concentration data of the monitoring point, compares the pollutant concentration data with the seepage direction change value, screens the monitoring points where the change range of the pollutant concentration exceeds the concentration change threshold, and calculates the offset amplitude between the pollutant diffusion direction and the path points according to the spatial position and the flow direction azimuth parameter of the screened monitoring points to obtain the main pollutant diffusion path result;

[0043] According to the main pollutant diffusion path result, the pollution diffusion path module obtains the pollutant concentration change value and the water flow velocity data of the path points, compares the pollutant diffusion rate of the path points according to the pollutant concentration change value and the water flow velocity data, screens the path points where the diffusion rate exceeds the diffusion rate threshold, and establishes an evaluation result of the pollutant diffusion trend according to the number of the screened path points and the flow direction azimuth parameter;

[0044] Based on the evaluation result of the pollutant diffusion trend, the early warning level determination module obtains the pollutant diffusion path data and the permeability characteristic data of the corresponding path points, compares the pollutant diffusion path data and the permeability characteristic data one by one, screens the path points where the permeability characteristic parameters exceed the diffusion risk threshold, and performs weighted calculation according to the number of the screened path points and the evaluation result of the pollutant diffusion trend to obtain the pollution diffusion early warning level result.

[0045] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0046] In the present invention, multi-source data are integrated and analyzed, the relationship between the groundwater flow pattern and the water quality change is clarified, the influence of meteorological changes on the groundwater is captured in time, the pollutant diffusion path, rate and influence range are accurately evaluated, the timeliness and accuracy of pollution early warning are improved, and the monitoring response speed is increased by automatic data processing, providing timely and accurate decision-making support for groundwater resource management and pollution prevention and control. Description of the Drawings

[0047] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for description in the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other accompanying drawings can be obtained based on these drawings without creative efforts.

[0048] Figure 1 It is a schematic diagram of the step flow of the present invention.

[0049] Figure 2 It is a system module diagram of the present invention. Specific embodiments

[0050] The following will describe the technical solutions in the present invention in conjunction with the accompanying drawings.

[0051] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to represent examples, illustrations or explanations. Any embodiment or design solution described as an "example" in the present invention should not be construed as being more preferred or more advantageous than other embodiments or design solutions. Exactly speaking, the use of the word "example" aims to present concepts in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one of the two.

[0052] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference is not emphasized, the meaning they express is the same. "(of)", "corresponding", and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference is not emphasized, the meaning they express is the same.

[0053] In the embodiments of the present invention, sometimes subscripts such as W1 may be written in a non-subscript form such as W1. When the difference is not emphasized, the meaning they express is the same.

[0054] To make the technical problems, technical solutions and advantages to be solved by the present invention clearer, the following will be described in detail in conjunction with the accompanying drawings and specific embodiments.

[0055] Please refer to Figure 1 , a groundwater monitoring and early warning method based on multi-source data fusion, including the following steps:

[0056] S1: Obtain the real-time data of water quality, flow rate, temperature, and pH sensors arranged in the monitoring area, adjust the data acquisition frequency according to the functional requirements of each monitoring point, verify and adjust the working status of the sensors based on the spatial distribution of the sensor layout, and form a water quality and geological feature data set;

[0057] S2: Invoke the water quality and geological feature data set, extract the parameters of aquifer thickness and flow azimuth angle, combine with the real-time precipitation and temperature data, analyze the dynamic changes of soil permeability and water flow, identify the influence of precipitation and temperature changes on the groundwater flow pattern, extract the information related to water quality changes for the seepage trend changes under different meteorological conditions, and generate the real-time seepage trend result;

[0058] S3: Based on the real-time seepage trend result, extract the changes in seepage direction and flow azimuth angle, combine with the pollutant concentration data, analyze the pollutant diffusion paths between each monitoring point for the changes in pollutant concentration at different monitoring points, identify the diffusion range and main path of pollutants, and iteratively identify the diffusion direction to generate the pollutant diffusion main path result;

[0059] S4: According to the pollutant diffusion main path result, identify the pollutant concentration changes and water flow velocity data, analyze the characteristics of pollutant diffusion, identify the pollutant diffusion trends at different path points, judge the diffusion rate and influence range of pollutants based on the flow velocity and permeability characteristics, and generate the pollutant diffusion trend evaluation result;

[0060] S5: Based on the pollutant diffusion trend evaluation result, by analyzing the pollutant diffusion path and permeability characteristics one by one, combine with the set risk warning standard, judge the severity of pollution diffusion, output the warning level of pollution diffusion, and generate the pollution diffusion warning level result.

[0061] The water quality and geological feature data set includes water quality data, flow velocity data, temperature data, pH value data, sensor status, acquisition frequency adjustment, and monitoring point distribution. The real-time seepage trend result includes soil permeability, groundwater flow pattern, precipitation, temperature changes, seepage trend, and factors related to water quality changes. The pollutant diffusion main path result includes changes in seepage direction, flow azimuth angle, pollutant concentration changes, diffusion path, diffusion range, diffusion main path, and diffusion direction. The pollutant diffusion trend evaluation result includes pollutant concentration changes, flow velocity data, diffusion characteristics, diffusion path points, diffusion rate, and influence range. The pollution diffusion warning level result includes pollution diffusion path, permeability characteristics, risk warning standard, severity of pollution diffusion, and warning level.

[0062] The specific steps of S1 are as follows:

[0063] S101: Obtain the real-time data of sensors in the monitoring area, compare the data acquisition frequency according to the functional requirements of the monitoring points, and establish a data acquisition frequency offset value;

[0064] First, according to the monitoring and deployment plan for the monitoring area, the spatial numbers and functional type parameter information of each monitoring point are called. In this embodiment, the monitoring area contains 10 monitoring points numbered from S1 to S10, and the functional type parameters are divided into two categories: water quality monitoring and geological monitoring. Among them, monitoring points S1, S3, S5, S7, and S9 are set as water quality monitoring points, and the rest are set as geological monitoring points. Subsequently, the real-time sampling frequency data transmitted by each monitoring point is read one by one. In this example, the sampling frequencies of S1 to S10 are 0.82Hz, 1.00Hz, 1.79Hz, 1.48Hz, 1.81Hz, 1.22Hz, 0.95Hz, 1.73Hz, 1.15Hz, and 1.36Hz respectively. According to the functional type of the monitoring point, the sampling frequency reference value is set. The sampling frequency reference value for water quality monitoring points is 1.2Hz, and the sampling frequency reference value for geological monitoring points is 1.0Hz. The basis for setting the reference value is the sampling requirements of historical similar projects and the equipment performance parameters. By statistically analyzing the average sampling frequency of water quality monitoring sensors in past similar projects, which is about 1.2Hz, and the geological monitoring average is about 1.0Hz, and the lowest stable frequencies of the equipment are 1.2Hz and 1.0Hz respectively, this reference value is determined. After obtaining the real-time sampling frequency of the monitoring point and the functional requirement reference value, the frequency offset value is calculated one by one. The calculation method is the actual sampling frequency minus the functional requirement reference value to obtain the offset result. In the example, the offset value of S1 is 0.82 - 1.2 = -0.38Hz, S2 is 1.00 - 1.0 = 0Hz, S3 is 1.79 - 1.2 = 0.59Hz, S4 is 1.48 - 1.0 = 0.48Hz, S5 is 1.81 - 1.2 = 0.61Hz, and so on. After calculating the offset values of all monitoring points, the offset values are classified according to the threshold standard. The offset value threshold is set to -0.2Hz to 0.5Hz. The basis for the threshold is the statistical analysis of historical data in the past 12 months. Monitoring points exceeding this range have sampling anomalies. The offset value of S1 is -0.38Hz, which is lower than -0.2Hz and is marked as abnormal. The offset value of S2 is 0Hz and is normal. The offset value of S3 is 0.59Hz, which is higher than 0.5Hz and is abnormal. The offset value of S4 is 0.48Hz and is normal. The offset value of S5 is 0.61Hz and is abnormal. All monitoring points are marked in this way, and finally a complete monitoring point sampling frequency offset value table and an abnormal marking table are formed.

[0065] S102: Based on the data acquisition frequency offset value, call the spatial distribution coordinates, detect the offset value difference between adjacent monitoring points, mark the monitoring points exceeding the spatial distribution difference threshold, and generate the abnormal distribution quantity of the monitoring points;

[0066] First, the spatial coordinate parameter information of the monitoring points is called one by one. In this embodiment, the spatial coordinates of the monitoring points S1 to S10 are S1(488.19, 110.75), S2(440.92, 337.56), S3(466.82, 145.83), S4(292.08, 200.99), S5(177.88, 227.52), S6(215.75, 471.67), S7(309.35, 155.82), S8(155.62, 122.25), S9(328.55, 407.92), S10(302.74, 367.83) respectively. Subsequently, the difference detection of the sampling frequency offset values of adjacent monitoring points is carried out in sequence. The selection rule for adjacent monitoring points is the pair of monitoring points with an Euclidean distance less than 150 meters. The basis for setting the 150-meter threshold is the spatial density of the monitoring area. In the past three projects, the average distance between adjacent monitoring points was 120 to 130 meters. To avoid missing the interference of adjacent points, it is set to 150 meters. During the calculation process, for each pair of adjacent monitoring points, two offset value difference operations are performed, and the absolute value is taken as the spatial offset difference value. For example, the distance between S1 and S3 is 45.21 meters, and the offset values are -0.38 Hz and 0.59 Hz. The spatial offset difference value is |-0.38 - 0.59| = 0.97 Hz. Subsequently, it is compared with the spatial distribution difference threshold, and the threshold is set to 0.8 Hz. According to the statistics of the spatial distribution abnormal critical values in historical monitoring projects, when it exceeds 0.8 Hz, it usually corresponds to equipment failure or environmental abnormality. In the example, the spatial offset difference value between S1 and S3 is 0.97 Hz, exceeding the threshold, and it is marked as abnormal distribution. Continue to perform the pairing detection of all adjacent monitoring points, complete the calculation of the offset difference value and the comparison with the threshold one by one. Finally, count all the monitoring point pairs that exceed the threshold to form the result of the abnormal distribution quantity of the monitoring points. In the example, both S1 and S3, and S5 and S7 have the phenomenon of exceeding the threshold, and the abnormal distribution quantity is counted as 2 groups of monitoring point pairs.

[0067] S103: According to the abnormal distribution quantity of the monitoring points, screen the working state parameters of the abnormal monitoring points, adjust the states of the monitoring points below the signal efficiency threshold, and obtain the data set of water quality and geological characteristics;

[0068] First, screen the list of abnormal monitoring points. In this embodiment, the abnormal distribution quantity results in the previous step involve monitoring points S1, S3, S5, and S7, a total of 4 monitoring points. Subsequently, call the working state parameters of these 4 monitoring points. The parameter items include signal efficiency, water quality characteristic values, and geological characteristic values. In the example, the signal efficiency of S1 is 53.2%, that of S3 is 99.7%, that of S5 is 63.3%, and that of S7 is 84.6%. Then, judge the status parameters of the monitoring points according to the signal efficiency threshold. The signal efficiency threshold is set to 70%. The setting basis is the calibration value in the equipment instruction manual and the historical monitoring stable operation data. In the historical data of the past 5 years, when the signal efficiency is lower than 70%, the abnormal probability of sensor sampling is greater than 60%. Therefore, 70% is set as the threshold. When performing the judgment, compare the signal efficiency of each abnormal monitoring point with 70%. The signal efficiency of S1 is 53.2%, lower than 70%, so it is judged as inefficient. The signal efficiency of S3 is 99.7%, higher than 70%, so it is normal. The signal efficiency of S5 is 63.3%, lower than 70%, so it is inefficient. The signal efficiency of S7 is 84.6%, so it is normal. Screen out the inefficient monitoring points S1 and S5. Subsequently, call the water quality characteristic data and geological characteristic data of S1 and S5. In the example, the water quality pH value of S1 is 5.80, and the geological parameter is 32.9. The water quality pH value of S5 is 7.61, and the geological parameter is 0.7. Finally, form a water quality and geological characteristic data set of inefficient monitoring points, and the result is S1 (pH 5.80, geology 32.9), S5 (pH 7.61, geology 0.7).

[0069] The specific steps of S2 are as follows:

[0070] S201: Call the water quality and geological characteristic data set, extract the aquifer thickness and flow azimuth angle parameters, combine the real-time precipitation and temperature data, calculate the difference values between the aquifer thickness and flow azimuth angle and precipitation and temperature, and establish the dynamic change value of the aquifer;

[0071] First, extract the water quality and geological feature data corresponding to the abnormal monitoring points screened in the previous steps one by one. In this embodiment, the feature data of monitoring points S1 and S5 have been obtained. Among them, the geological feature data of S1 is 32.9, and that of S5 is 0.7. Subsequently, extract the aquifer thickness parameter from the geological feature data. The extraction method is to directly read the thickness field in the corresponding geological feature data. In the example, the aquifer thickness of S1 is set to 32.9 meters, and that of S5 is 0.7 meters. The thickness data is derived from on-site drilling measurements and sensor inversion data. Immediately afterwards, extract the flow azimuth angle parameter. The parameter acquisition method is to call the flow direction field in the geological feature data of the monitoring point. In the example, the azimuth angle of S1 is 135°, and that of S5 is 80°. The flow azimuth angle data is entered based on the on-site geological mapping results. Subsequently, call the real-time precipitation and temperature data within the monitoring area. The data source is automatic collection by the meteorological station. In the example, the real-time precipitation in the S1 area is 12.5 mm, and the temperature is 26.4 °C. The precipitation in the S5 area is 9.8 mm, and the temperature is 28.1 °C. After completing the data acquisition, calculate the difference values between the aquifer thickness and precipitation, and temperature in turn. Specifically, it is the thickness value minus the mean of precipitation and temperature multiplied by the scaling factor. The scaling factor is set to 0.5, and the setting basis is the mean of the response coefficients of precipitation and temperature to the change of aquifer thickness in historical monitoring data. In the example, the calculation process for S1 is 32.9 - [(12.5 + 26.4) / 2 × 0.5] = 32.9 - [19.45 × 0.5] = 32.9 - 9.725 = 23.175 meters, and for S5 it is 0.7 - [(9.8 + 28.1) / 2 × 0.5] = 0.7 - [18.95 × 0.5] = 0.7 - 9.475 = -8.775 meters. Then, calculate the difference values between the flow azimuth angle and precipitation, and temperature. The calculation method is the flow azimuth angle minus the mean of precipitation and temperature. For S1, it is 135 - (12.5 + 26.4) / 2 = 135 - 19.45 = 115.55°, and for S5 it is 80 - (9.8 + 28.1) / 2 = 80 - 18.95 = 61.05°. Finally, summarize the thickness difference value and the flow azimuth angle difference value to form the dynamic change value of the aquifer at the monitoring point. In the example, the dynamic change value of S1 is a thickness difference of 23.175 meters and a flow difference of 115.55°, and for S5 it is a thickness difference of -8.775 meters and a flow difference of 61.05°.

[0072] S202: Based on the dynamic change value of the aquifer, call the real-time precipitation and temperature data, extract the change ranges of precipitation and temperature, and compare the permeability parameter and the water flow direction parameter with the change ranges of precipitation and temperature according to the change ranges of precipitation and temperature. Screen the monitoring points with a difference range exceeding the seepage change threshold, and generate the seepage change trend related to meteorological conditions;

[0073] First, the real-time precipitation and temperature data within the monitoring area are called one by one. In the example, the real-time precipitation at monitoring point S1 is 12.5 mm and the temperature is 26.4 °C. The precipitation at S5 is 9.8 mm and the temperature is 28.1 °C. Subsequently, the change ranges of precipitation and temperature are extracted. The calculation method of the change range is the current value minus the average value of the past 24 hours. In the example, the average precipitation of S1 in the past 24 hours is 8.2 mm and the average temperature is 25.6 °C. The average precipitation of S5 in the past 24 hours is 10.1 mm and the average temperature is 27.4 °C. The precipitation change range of S1 is 12.5 - 8.2 = 4.3 mm, and the temperature change range is 26.4 - 25.6 = 0.8 °C. The precipitation change range of S5 is 9.8 - 10.1 = -0.3 mm, and the temperature change range is 28.1 - 27.4 = 0.7 °C. Then, the permeability parameter and water flow direction parameter in the geological feature data of the monitoring points are called. The permeability parameter of S1 is 0.85 and that of S5 is 0.65. The water flow direction parameter of S1 is 130° and that of S5 is 78°. Next, the permeability parameter, water flow direction parameter are compared with the change ranges of precipitation and temperature. The comparison method is that the permeability parameter is multiplied by the sum of the precipitation change range and the temperature change range, and the water flow direction parameter minus the sum of the precipitation and temperature change ranges. In the example, the permeability comparison value of S1 is 0.85×(4.3 + 0.8) = 4.335, and the water flow direction comparison value is 130 - (4.3 + 0.8) = 124.9°. The permeability comparison value of S5 is 0.65×(-0.3 + 0.7) = 0.26, and the water flow direction comparison value is 78 - (-0.3 + 0.7) = 77.6°. Then, the comparison results are screened according to the seepage change threshold. The seepage change threshold is set to 3.5. According to the statistics of the monitoring data in the past 12 months, when the permeability comparison value of the monitoring point exceeds 3.5, the abnormal probability of the seepage change trend exceeds 65%. In the example, the permeability comparison value of S1 is 4.335, which is greater than 3.5 and is marked as abnormal change. That of S5 is 0.26, which is less than 3.5 and is marked as normal. Finally, the result of the seepage change trend related to meteorological conditions is formed. In the example, there is a seepage change trend at monitoring point S1 and no change trend at S5.

[0074] S203: According to the seepage change trend related to meteorological conditions, extract the turbidity value and conductivity value in the water quality parameters of the monitoring points, judge the correlation between the seepage change trend and the water quality parameter change trend of the corresponding monitoring points, extract the data of the monitoring points with correlation, and obtain the real-time seepage trend result;

[0075] First, screen the monitoring points marked with seepage change trends in the previous steps. In this embodiment, it is the S1 monitoring point. Subsequently, call the turbidity value and conductivity value in the real-time water quality parameters of the S1 monitoring point. The current turbidity value of S1 is 23.7 NTU, and the conductivity value is 420 μS / cm. Extract the change range of the water quality parameters of this monitoring point within the past 24 hours. The calculation method of the change range is the current value minus the average value of the past 24 hours. The average turbidity of S1 in the past 24 hours is 19.4 NTU, and the average conductivity is 405 μS / cm. The change range is turbidity 23.7 - 19.4 = 4.3 NTU, and conductivity 420 - 405 = 15 μS / cm. Subsequently, judge the correlation between the seepage change trend and the water quality parameter change trend. The judgment method is to compare whether the seepage change trend mark and the water quality parameter change range appear abnormally synchronously. The specific judgment rule is that when the turbidity change range is greater than 3 NTU and the conductivity change range is greater than 10 μS / cm, it is judged that there is a correlation. The threshold is based on historical data analysis. In the data of the past three years, when the turbidity change range exceeds 3 NTU and the conductivity change range exceeds 10 μS / cm, the synchronous probability of the seepage change trend and the water quality parameter change is greater than 70%. In the example, the turbidity change range of S1 is 4.3 NTU, which is greater than 3 NTU, and the conductivity change range is 15 μS / cm, which is greater than 10 μS / cm, meeting the correlation judgment conditions. Finally, extract the data of the monitoring points with correlation, and the result is the real-time seepage trend result of the S1 monitoring point.

[0076] The specific steps of S3 are as follows:

[0077] S301: Based on the real-time seepage trend result, extract the seepage direction change parameter and the flow azimuth angle data, compare the two parameters according to the spatial coordinates of the monitoring point, and establish the seepage direction change value;

[0078] First, call the seepage trend data of the monitoring points obtained in the previous steps one by one. In this embodiment, it has been determined that there is a change in the seepage trend at the monitoring point S1. Subsequently, extract the seepage direction change parameters corresponding to the S1 monitoring point. The parameter acquisition method is to compare the current water flow direction of the monitoring point with the average water flow direction in the past 48 hours. The current water flow direction data comes from the real-time monitoring results of the sensor. In the example, the current seepage direction of S1 is 138°, and the average water flow direction in the past 48 hours is 130°. The seepage direction change parameter is calculated as 138° - 130° = 8°. Then, extract the flow azimuth angle data corresponding to the S1 monitoring point. The data source is the preset value in the geological feature data table. In the example, the flow azimuth angle of S1 is 135°. Subsequently, call the spatial coordinate parameters of the monitoring point. The spatial coordinate of S1 is (488.19, 110.75). Based on the spatial coordinates of the monitoring point and the flow azimuth angle data, compare the spatial correspondence relationship between the seepage direction change parameter and the flow azimuth angle. The comparison method is to calculate the angle difference between the seepage direction change parameter and the flow azimuth angle. The angle difference of S1 is |8° - 135°| = 127°. Subsequently, according to the spatial distribution of the monitoring points, call the spatial coordinates and azimuth angle parameters of the adjacent monitoring points. In the example, the spatial coordinate of the adjacent monitoring point S3 is (466.82, 145.83), and the azimuth angle is 125°. Similarly, calculate the seepage direction change parameter of S3. The current seepage direction of S3 is 120°, the average value in the past 48 hours is 115°, the change parameter is 5°, and the angle difference is |5° - 125°| = 120°. Finally, archive the seepage direction change parameters and the angle differences of the flow azimuth angles of each monitoring point to establish the seepage direction change values in the monitoring area. In the example, the change value of S1 is 8° and the angle difference is 127°, and the change value of S3 is 5° and the angle difference is 120°.

[0079] S302: According to the seepage direction change value, call the pollutant concentration data, extract the change range of the pollutant concentration at the monitoring point, and perform a comparison process based on the concentration change range and the seepage direction change. Screen the monitoring points where the concentration change range exceeds the pollutant concentration change threshold and the corresponding seepage direction change value is greater than the flow direction change reference value to generate the pollutant diffusion trend interval;

[0080] First, the pollutant concentration data at each monitoring point is called one by one. In this embodiment, the current pollutant concentration at monitoring point S1 is 4.8 mg / L, and the average concentration in the past 24 hours is 3.2 mg / L. The current concentration at S3 is 5.1 mg / L, and the average in the past 24 hours is 4.7 mg / L. Subsequently, the change range of the pollutant concentration at the monitoring point is extracted. The calculation method is the current concentration minus the average concentration in the past 24 hours. The change range of S1 is 4.8 - 3.2 = 1.6 mg / L, and the change range of S3 is 5.1 - 4.7 = 0.4 mg / L. Then, according to the change range of the concentration and the change of the seepage direction, a comparison process is carried out. The comparison method is to simultaneously judge whether two conditions are met. The first condition is whether the change range of the concentration exceeds the pollutant concentration change threshold, and the second condition is whether the change value of the seepage direction at the corresponding monitoring point is greater than the flow direction change reference value. The pollutant concentration change threshold is set to 1.0 mg / L, based on the statistical data of the monitoring data in the past two years. When the change range of the concentration exceeds 1.0 mg / L, the pollutant diffusion probability is greater than 70%. The flow direction change reference value is set to 6°, based on the statistical data of the geological conditions and hydrological monitoring data. When the change of the seepage direction exceeds 6°, it has a significant impact on the pollutant migration path. In the example, the change range of the concentration at S1 is 1.6 mg / L, which is greater than 1.0 mg / L, and the change value of the seepage direction is 8°, which is greater than 6°, meeting the conditions. The change range of the concentration at S3 is 0.4 mg / L, which is less than 1.0 mg / L, not meeting the conditions. The screening result is that the S1 monitoring point meets the comparison conditions, and finally a pollutant diffusion trend interval is formed, and the interval range covers the S1 monitoring point.

[0081] S303: Based on the pollutant diffusion trend interval, extract the spatial distribution coordinates and flow direction azimuth data of the monitoring points. According to the change parameters of the spatial coordinates of the monitoring points and the diffusion trend interval, calculate the pollutant diffusion path direction continuity index, screen the paths with the direction continuity coefficient greater than the path recognition threshold, and obtain the pollutant diffusion main path result;

[0082] The specific calculation formula for the pollutant diffusion path direction continuity index is as follows:

[0083]

[0084] Among them, C d represents the pollutant diffusion path direction continuity index, θ i represents the flow direction azimuth data of the i-th monitoring point, X i represents the X coordinate value of the spatial distribution coordinates of the i-th monitoring point, Y i represents the Y coordinate value of the spatial distribution coordinates of the i-th monitoring point, D i represents the change parameter of the diffusion trend interval of the i-th monitoring point, and n represents the total number of monitoring points in the path;

[0085] The given monitoring point data includes the spatial coordinates (Xi , Y i ), flow azimuth angle θ i , and the change D in pollutant concentration i . The data example of the monitoring points is three points, and their parameters are as follows:

[0086] Monitoring point 1: Coordinates (488.19, 110.75), azimuth angle 135°, pollutant concentration change 0.1;

[0087] Monitoring point 2: Coordinates (480.00, 120.00), azimuth angle 140°, pollutant concentration change 0.15;

[0088] Monitoring point 3: Coordinates (470.00, 130.00), azimuth angle 145°, pollutant concentration change 0.2;

[0089] The steps to calculate the direction continuity index C of the pollutant diffusion path are as follows: d are as follows:

[0090] Calculate the total difference between azimuth angles:

[0091]

[0092] Calculate the total Euclidean distance between monitoring points:

[0093]

[0094] Calculate the total change in pollutant concentration:

[0095]

[0096] Apply the formula to calculate C d :

[0097]

[0098] The result shows that the direction continuity index C of the pollutant diffusion path d is 63.84. This value represents a comprehensive evaluation index of the azimuth difference, position change, and pollutant concentration change between monitoring points. A high value indicates that under a small change in pollutant concentration, the direction and position change of the path are large, indicating that the possible pollution diffusion path is more complex or dispersed. According to this index, the paths with a direction continuity coefficient greater than a specific threshold can be further screened out, which helps to identify the main pollution diffusion paths and provides decision-making support for further pollution control and treatment.

[0099] The specific steps of S4 are as follows:

[0100] S401: According to the results of the main pollutant diffusion path, extract the pollutant concentration change parameters and water flow velocity data at the path points. Based on the comparison of the spatial coordinates of the path points and the pollutant concentration change parameters, establish the pollutant diffusion value at the path points.

[0101] First, call the obtained results of the main pollutant diffusion path one by one. In this embodiment, the main path consists of monitoring points S1 and S3. Subsequently, extract the pollutant concentration change parameters corresponding to the path points. The parameter extraction method is to call the current pollutant concentration at the monitoring point and the average concentration in the past 24 hours, and calculate the change amplitude. In the example, the current concentration at S1 is 4.8 mg / L, the 24-hour average value is 3.2 mg / L, and the change amplitude is 1.6 mg / L. The current concentration at S3 is 5.1 mg / L, the average value is 4.7 mg / L, and the change amplitude is 0.4 mg / L. Immediately afterwards, extract the water flow velocity data at the path points. The data source is the real-time monitoring device. The water flow velocity at S1 is 0.45 m / s, and at S3 is 0.38 m / s. Subsequently, based on the spatial coordinates of the path points, compare the pollutant concentration change parameters. The spatial coordinates of the path point S1 are (488.19, 110.75), and those of S3 are (466.82, 145.83). The comparison process is to calculate the correlation between the pollutant concentration change amplitude and the change in the spatial distance of the path points. The calculation method of the spatial distance of the path points is the Euclidean distance. The spatial distance between S1 and S3 is √[(488.19 - 466.82) 2 +(110.75 - 145.83) 2 = 41.9 meters. Subsequently, calculate the pollutant diffusion value. The calculation method is the concentration change amplitude divided by the spatial distance. The diffusion value from S1 to S3 is (1.6 + 0.4) / 41.9 = 0.0477 mg / L·m-1. Finally, archive the diffusion value, the spatial coordinates of the path points, and the concentration change parameters to form a dataset of pollutant diffusion values at the path points. The example result is that the diffusion value of path S1 - S3 is 0.0477 mg / L·m-1.

[0102] S402: Based on the pollutant diffusion value at the path points, call the permeability parameter and water flow velocity data at the path points, calculate the diffusion rate index between the permeability parameter and the water flow velocity at the path points. Based on the comparison of the diffusion rate coefficient and the pollutant concentration change amplitude at the path points, screen the path points where both the diffusion rate coefficient and the concentration change amplitude exceed the diffusion rate benchmark value, and generate the diffusion rate change trend.

[0103] The specific calculation formula for the diffusion rate index value of the path points is:

[0104]

[0105] Among them, R e represents the diffusion rate index value of the path points, K k represents the permeability parameter of the kth path point, Sk represents the water flow velocity data of the k-th path point, C k represents the change amplitude of pollutant concentration at the k-th path point, represents the average value of the change amplitude of pollutant concentration at path points, M represents the number of path points;

[0106] Path point diffusion rate index value R e In the calculation process of, the sources of all parameters are monitoring data or monitoring calculations. The number of path points M is determined by the number of monitored path points. In the current example, it is set that the path contains 3 monitoring points, which are obtained through on-site layout and spatial coordinate acquisition methods.

[0107] Path point permeability parameter K k The value source of is field borehole test and hydrogeological inversion data. The unit of the permeability parameter is m / d. According to the value range of the permeability parameter of the confined aquifer in the "Technical Specification for Groundwater Monitoring" in China, it is set to 0.85 m / d, 0.92 m / d, and 0.88 m / d.

[0108] Path point water flow velocity data S k The source is real-time acquisition by flow velocity monitoring equipment. The flow velocity values at the monitoring points are 0.46 m / s, 0.51 m / s, and 0.49 m / s. The value range is set with reference to the average flow velocity range of general river channels and underground seepage monitoring in the "Technical Specification for Surface Water Flow Velocity Monitoring".

[0109] Path point pollutant concentration change amplitude C k It is calculated by the pollutant monitoring equipment from the current and average concentrations in the past 24 hours. The monitoring data is the difference between the current concentration and the average value in the past 24 hours, and the values are 1.4 mg / L, 1.8 mg / L, and 1.6 mg / L.

[0110] Average value of pollutant concentration change amplitude It is obtained by averaging the concentration change amplitudes of each monitoring point. The calculation process is as follows:

[0111]

[0112] The formula operation steps are as follows:

[0113] Calculate the sum of the products of permeability and water flow velocity:

[0114]

[0115] Calculate the sum of the absolute values of the deviations between the pollutant concentration change amplitude and the average value:

[0116]

[0117] Calculate the sum of the squares of the water flow velocity and take the square root:

[0118]

[0119] Substitute into the formula to calculate the diffusion rate index value:

[0120]

[0121] The result shows that the diffusion rate index value in the current path is 0.668, representing the degree of co-diffusion characteristics of the permeability parameter, water flow velocity, and pollutant concentration change amplitude at the path point in the current path. This value will serve as an important criterion for screening path points where both the diffusion rate coefficient and the concentration change amplitude exceed the diffusion rate reference value in the subsequent steps, and is directly related to the final result determination of the diffusion rate change trend.

[0122] S403: According to the diffusion rate change trend, extract the spatial distribution coordinates of the path points. Based on the diffusion rate change trend and spatial coordinates of the path points, judge the coverage range of the diffusion trend, and establish the pollutant diffusion trend assessment result;

[0123] First, extract the spatial distribution coordinates of the path points with the diffusion rate change trend that have been screened. In this embodiment, it is the monitoring point S1, and the spatial coordinates are (488.19, 110.75). Subsequently, call the diffusion rate change trend data of the path points. In the example, the diffusion rate index of S1 is 0.3825, and the pollutant concentration change amplitude is 1.6 mg / L. Based on the diffusion rate change trend and spatial coordinates of the path points, judge the coverage range of the diffusion trend. The judgment process is to first determine the spatial distribution boundary of the diffusion trend path points, specifically by obtaining the minimum and maximum coordinate values of all path points. Currently, there is only S1, and the boundary range is (488.19, 110.75). Subsequently, calculate the spatial distance from the adjacent monitoring point to the trend path point. In the example, the coordinates of the adjacent monitoring point S3 are (466.82, 145.83), and the spatial distance from S1 is 41.9 meters. Set the spatial coverage threshold to 50 meters, based on the statistical mean of the diffusion radius of historical diffusion events. Judge whether S3 is within the coverage range. The distance of S3 is 41.9 meters, which is less than 50 meters, and it is marked as within the coverage range. Finally, establish the pollutant diffusion trend assessment result, and the result is that the monitoring point S1 and its adjacent point S3 are within the coverage range of the pollutant diffusion trend.

[0124] The specific steps of S5 are as follows:

[0125] S501: Based on the pollutant diffusion trend assessment result, extract the pollutant diffusion path parameters and permeability characteristic data. Compare the path points according to the path parameters and permeability characteristics, and establish the diffusion characteristic value of the path points;

[0126] First, call the assessment results of the pollutant diffusion trend established in the previous steps. In this embodiment, the diffusion trend covers monitoring points S1 and S3. Subsequently, extract the main path parameters. The path parameters include a sequence of path points and their corresponding spatial coordinates. In the example, the spatial coordinates of path point S1 are (488.19, 110.75), and those of S3 are (466.82, 145.83). The path sequence is S1→S3. Then, extract the permeability characteristic data of the path points. The data is sourced from the geological characteristic data of the monitoring points. The permeability parameter of S1 is 0.85, and that of S3 is 0.75. Subsequently, compare the path points based on the path parameters and permeability characteristics. The comparison process involves associating the permeability parameter corresponding to the spatial coordinates of each path point with the pollutant concentration change amplitude in the pollutant diffusion trend. The concentration change amplitude of S1 is 1.6 mg / L, and that of S3 is 0.4 mg / L. Then, calculate the diffusion characteristic value of the path points. The calculation method is the product of the concentration change amplitude and the permeability parameter. In the example, the diffusion characteristic value of S1 is 1.6×0.85 = 1.36, and that of S3 is 0.4×0.75 = 0.3. Subsequently, establish a one-to-one correspondence between the diffusion characteristic values and the spatial coordinates of the path points, and archive them to form a data set of diffusion characteristic values of path points. The example result is that the diffusion characteristic value of S1 is 1.36, and that of S3 is 0.3.

[0127] S502: According to the diffusion characteristic values of the path points, call the set risk warning criteria, extract the pollutant concentration change amplitude and diffusion rate data from the diffusion characteristic values of the path points, and compare the pollutant concentration change amplitude and diffusion rate with the threshold values of the risk warning criteria to judge the diffusion risk of the path points and generate the risk level value of the path points;

[0128] First, call the set risk warning standard. The standard parameters include the threshold of the change range of pollutant concentration and the reference value of the diffusion rate. The threshold of the change range of pollutant concentration is set to 1.0 mg / L, based on the fact that when the change range of concentration in historical monitoring projects exceeds 1.0 mg / L, the probability of risk events is greater than 70%. The reference value of the diffusion rate is set to 0.3, based on the historical statistical results of permeability parameters and water flow velocity. When the diffusion rate index exceeds 0.3, the corresponding diffusion risk increases significantly. In this embodiment, the change range of pollutant concentration and the diffusion rate data in the diffusion characteristics of path points are extracted one by one. The change range of S1 concentration is 1.6 mg / L, and the diffusion rate is 0.3825. The change range of S3 concentration is 0.4 mg / L, and the diffusion rate is 0.285. Subsequently, the change range of pollutant concentration and the diffusion rate of path points are compared with the threshold of the risk warning standard. The comparison process is to judge point by point whether two conditions are met at the same time. The first condition is whether the change range of pollutant concentration is greater than 1.0 mg / L, and the second condition is whether the diffusion rate is greater than 0.3. In the example, the change range of S1 concentration is 1.6 mg / L, which is greater than 1.0 mg / L, and the diffusion rate is 0.3825, which is greater than 0.3, meeting the conditions and being judged as a high-risk level. The change range of S3 concentration is 0.4 mg / L, which is less than 1.0 mg / L, not meeting the conditions and being judged as a low-risk level. Finally, the risk level values of path points are generated. S1 is a high risk, and S3 is a low risk.

[0129] S503: According to the risk level values of path points, extract all the spatial coordinate data of path points. According to the spatial coordinates and the risk level values, calculate the spatial distribution density of path points with risk levels, judge whether the distribution density exceeds the risk warning threshold, and establish the result of the pollution diffusion warning level;

[0130] First, extract all the spatial coordinate data of the path points. In this embodiment, the coordinates of path point S1 are (488.19, 110.75), and those of S3 are (466.82, 145.83). Subsequently, extract the corresponding risk level values of the path points. S1 is a high - risk point, and S3 is a low - risk point. Based on the spatial coordinates and the risk level values, calculate the spatial distribution density of the risk - level path points. The calculation process is to count the number of high - risk path points and divide it by the area of the spatial region. In the current embodiment, only S1 is a high - risk point, the total number of path points is 2, the regional boundary is a rectangular area formed by the maximum and minimum values of the spatial coordinates of the path points. The area of the region is calculated as |488.19 - 466.82|×|145.83 - 110.75| = 21.37×35.08 = 749.98 square meters. The spatial distribution density is 1 / 749.98≈0.00133 points per square meter. Subsequently, determine whether the distribution density exceeds the risk warning threshold. The risk warning threshold is set to 0.001 points per square meter, based on the statistical data of the historical data in the monitoring area in the past five years. When the spatial distribution density exceeds this threshold, the probability of the diffusion event occurring exceeds 75%. In the current embodiment, the distribution density of 0.00133 is greater than 0.001, which is determined to exceed the risk warning threshold. Finally, establish the pollution diffusion warning level result, and the result is that the current monitoring area reaches the pollution diffusion warning state.

[0131] Please refer to Figure 2 , a groundwater monitoring and early warning system based on multi - source data fusion, comprising:

[0132] The sensing data acquisition module acquires the data of water quality sensors, flow velocity sensors, temperature sensors, and pH value sensors deployed in the monitoring area, adjusts the data acquisition frequency according to the functional requirements of the monitoring points, verifies the working status of the sensors based on the spatial distribution of the sensors, and adjusts the abnormal data acquisition parameters to establish a data set of water quality and geological characteristics.

[0133] The characteristic parameter extraction module calls the data set of water quality and geological characteristics, extracts the aquifer thickness parameter and the flow direction azimuth parameter of the monitoring points, acquires the real - time precipitation data and air temperature data in the monitoring area, compares the change range of the aquifer thickness parameter according to the real - time precipitation data, identifies the influence of precipitation and air temperature changes on the aquifer thickness, and establishes the real - time seepage trend result.

[0134] The seepage trend analysis module, based on the real - time seepage trend result, obtains the seepage direction change value and the flow direction azimuth parameter of the monitoring points, acquires the pollutant concentration data of the monitoring points, compares the pollutant concentration data with the seepage direction change value, screens out the monitoring points whose pollutant concentration change range exceeds the concentration change threshold, and calculates the offset amplitude between the pollutant diffusion direction and the path points based on the spatial positions and the flow direction azimuth parameters of the screened monitoring points to obtain the main path result of pollutant diffusion.

[0135] Based on the results of the main pollutant diffusion path, the pollution diffusion path module obtains the pollutant concentration change values and water flow velocity data of the path points, compares the pollutant diffusion rates of the path points according to the pollutant concentration change values and water flow velocity data, screens the path points with diffusion rates exceeding the diffusion rate threshold, and establishes the pollutant diffusion trend assessment results based on the number of screened path points and the flow direction azimuth angle parameter;

[0136] Based on the pollutant diffusion trend assessment results, the early warning level determination module obtains the pollutant diffusion path data and permeability characteristic data of the corresponding path points, compares them one by one for the pollutant diffusion path data and permeability characteristic data, screens the path points with permeability characteristic parameters exceeding the diffusion risk threshold, and performs weighted calculation based on the number of screened path points and the pollutant diffusion trend assessment results to obtain the pollution diffusion early warning level results.

[0137] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A groundwater monitoring and early warning method based on multi-source data fusion, characterized in that It includes the following steps: S1: Obtain the real-time data of water quality, flow velocity, temperature, and pH sensors in the monitoring area, adjust the acquisition frequency according to functional requirements, calibrate and adjust the working status of the sensors, and form a water quality and geological feature data set; S2: Call the water quality and geological data set, extract the aquifer thickness and flow azimuth angle, analyze the soil permeability and water flow dynamics in combination with precipitation and temperature, identify the impact of meteorological condition changes on the groundwater flow pattern, and generate a real-time seepage trend result; S3: Based on the real-time seepage trend result, extract the seepage direction and flow azimuth angle, analyze the pollutant diffusion path, identify the pollutant diffusion range and main path, and generate a pollutant diffusion main path result; S4: According to the pollutant diffusion main path result, analyze the changes in pollutant concentration and water flow velocity, identify the diffusion characteristics and permeability impact, and judge the diffusion rate and influence range, and generate an evaluation result of the pollutant diffusion trend; S5: Combine the evaluation result of the pollutant diffusion trend, analyze the diffusion path and permeability, and evaluate the severity of pollution diffusion according to the set risk warning standard, and generate a pollution diffusion warning level result.

2. The groundwater monitoring and early warning method based on multi-source data fusion according to claim 1, wherein, The water quality and geological feature data set includes water quality data, flow velocity data, temperature data, pH value data, sensor status, acquisition frequency adjustment, and monitoring point distribution. The real-time seepage trend result includes soil permeability, groundwater flow pattern, precipitation, temperature change, seepage trend, and factors related to water quality change. The pollutant diffusion main path result includes changes in seepage direction, flow azimuth angle, pollutant concentration change, diffusion path, diffusion range, diffusion main path, and diffusion direction. The pollutant diffusion trend evaluation result includes pollutant concentration change, flow velocity data, diffusion characteristics, diffusion path points, diffusion rate, and influence range. The pollution diffusion warning level result includes pollution diffusion path, permeability characteristics, risk warning standard, severity of pollution diffusion, and warning level.

3. The groundwater monitoring and early warning method based on multi-source data fusion according to claim 1, characterized in that, The specific steps of S1 are: S101: Obtain the real-time data of sensors in the monitoring area, compare the data acquisition frequency according to the functional requirements of the monitoring points, and establish a data acquisition frequency offset value; S102: Based on the data acquisition frequency offset value, call the spatial distribution coordinates, detect the offset value difference between adjacent monitoring points, mark the monitoring points exceeding the spatial distribution difference threshold, and generate the abnormal distribution quantity of monitoring points; S103: According to the abnormal distribution quantity of the monitoring points, screen the working status parameters of the abnormal monitoring points, adjust the status of the monitoring points below the signal efficiency threshold, and obtain the water quality and geological feature data set.

4. The groundwater monitoring and early warning method based on multi-source data fusion according to claim 1, characterized in that The specific steps of S2 are: S201: Call the water quality and geological feature data set, extract the aquifer thickness and flow azimuth angle parameters, combine the real-time precipitation and temperature data, calculate the difference values between the aquifer thickness and flow azimuth angle and precipitation and temperature, and establish an aquifer dynamic change value; S202: Based on the dynamic change value of the aquifer, call the real-time precipitation and temperature data, extract the change ranges of precipitation and temperature. According to the change ranges of precipitation and temperature, compare the permeability parameter and the water flow direction parameter with the change ranges of precipitation and temperature, and screen out the monitoring points where the difference range exceeds the seepage change threshold, and generate the seepage change trend related to meteorological conditions. S203: According to the seepage change trend related to meteorological conditions, extract the turbidity value and conductivity value in the water quality parameters of the monitoring points, judge the relevance between the seepage change trend and the water quality parameter change trend of the corresponding monitoring points, extract the data of the monitoring points with relevance, and obtain the real-time seepage trend result.

5. The groundwater monitoring and early warning method based on multi-source data fusion according to claim 1, characterized in that, The specific steps of S3 are as follows: S301: Based on the real-time seepage trend result, extract the seepage direction change parameter and the flow direction azimuth angle data, and compare the two parameters according to the spatial coordinates of the monitoring points to establish the seepage direction change value. S302: According to the seepage direction change value, call the pollutant concentration data, extract the change range of the pollutant concentration at the monitoring points, and compare and process according to the change range of the concentration and the seepage direction change. Screen out the monitoring points where the change range of the concentration exceeds the pollutant concentration change threshold and the corresponding seepage direction change value is greater than the flow direction change reference value, and generate the pollutant diffusion trend interval. S303: Based on the pollutant diffusion trend interval, extract the spatial distribution coordinates and flow direction azimuth angle data of the monitoring points, calculate the pollutant diffusion path direction continuity index according to the spatial coordinates of the monitoring points and the change parameters of the diffusion trend interval, and screen out the paths where the direction continuity coefficient is greater than the path recognition threshold to obtain the pollutant diffusion main path result.

6. The groundwater monitoring and early warning method based on multi-source data fusion according to claim 1, characterized in that, The specific calculation formula of the pollutant diffusion path direction continuity index is as follows: Among them, C d represents the continuity index of the pollutant diffusion path direction, θ i represents the flow azimuth data of the i-th monitoring point, X i represents the X coordinate value of the spatial distribution coordinates of the i-th monitoring point, Y i represents the Y coordinate value of the spatial distribution coordinates of the i-th monitoring point, D i represents the change parameter of the diffusion trend interval of the i-th monitoring point, and n represents the total number of monitoring points in the path.

7. The groundwater monitoring and early warning method based on multi-source data fusion according to claim 1, characterized in that, The specific steps of S4 are as follows: S401: According to the pollutant diffusion main path result, extract the pollutant concentration change parameter and water flow velocity data of the path points, and compare according to the spatial coordinates of the path points and the pollutant concentration change parameter to establish the pollutant diffusion value of the path points. S402: Based on the pollutant diffusion value of the path points, call the permeability parameter and water flow velocity data of the path points, calculate the diffusion rate index between the permeability parameter and the water flow velocity of the path points, and compare according to the diffusion rate coefficient and the change range of the pollutant concentration at the path points. Screen out the path points where the diffusion rate coefficient and the change range of the concentration both exceed the diffusion rate reference value, and generate the diffusion rate change trend. S403: According to the diffusion rate change trend, extract the spatial distribution coordinates of the path points, and judge the diffusion trend coverage range according to the diffusion rate change trend and the spatial coordinates of the path points to establish the pollutant diffusion trend evaluation result.

8. The groundwater monitoring and early warning method based on multi-source data fusion according to claim 1, characterized in that, The specific calculation formula of the diffusion rate index value of the path points is as follows: wherein, R e represents the path point diffusion rate index value, K k represents the permeability parameter of the k-th path point, S k represents the water flow velocity data of the k-th path point, C k represents the change range of the pollutant concentration at the k-th path point, C represents the average value of the change range of the pollutant concentration at the path point, and M represents the number of path points.

9. The groundwater monitoring and early warning method based on multi-source data fusion according to claim 1, characterized in that The specific steps of S5 are as follows: S501: Based on the pollutant diffusion trend evaluation result, extract the pollutant diffusion path parameter and permeability characteristic data, and compare the path points according to the path parameter and the permeability characteristic to establish the pollutant diffusion characteristic value of the path points. S502: According to the path point diffusion eigenvalue, call the set risk warning standard, extract the pollutant concentration change amplitude and diffusion rate data in the path point diffusion eigenvalue, and judge the path point diffusion risk and generate a path point risk level value based on the comparison of the pollutant concentration change amplitude and diffusion rate with the threshold value of the risk warning standard; S503: According to the path point risk level value, extract all path point spatial coordinate data, calculate the spatial distribution density of the risk level path points according to the spatial coordinates and risk level values, judge whether the distribution density exceeds the risk warning threshold, and establish a pollution diffusion warning level result.

10. A groundwater monitoring and early warning system based on multi-source data fusion, characterized in that, A groundwater monitoring and warning method based on multi-source data fusion according to any one of claims 1-9, the system comprising: The sensing data acquisition module acquires water quality sensor data, flow velocity sensor data, temperature sensor data and pH value sensor data arranged in the monitoring area, adjusts the data acquisition frequency according to the functional requirements of the monitoring points, checks the working status of the sensors according to the spatial distribution of the sensors and adjusts the abnormal data acquisition parameters, and establishes a water quality and geological feature data set; The characteristic parameter extraction module calls the water quality and geological feature data set, extracts the aquifer thickness parameter and flow direction azimuth parameter of the monitoring point, acquires the real-time precipitation data and air temperature data in the monitoring area, compares the change amplitude of the aquifer thickness parameter according to the real-time precipitation data, identifies the influence of precipitation and temperature changes on the aquifer thickness, and establishes a real-time seepage trend result; The seepage trend analysis module, based on the real-time seepage trend result, acquires the seepage direction change value and flow direction azimuth parameter of the monitoring point, acquires the pollutant concentration data of the monitoring point, compares the pollutant concentration data with the seepage direction change value, screens out the monitoring points where the pollutant concentration change amplitude exceeds the concentration change threshold, and calculates the offset amplitude between the pollutant diffusion direction and the path points according to the spatial position and flow direction azimuth parameter of the screened monitoring points to obtain the main pollutant diffusion path result; The pollution diffusion path module, according to the main pollutant diffusion path result, acquires the pollutant concentration change value and water flow velocity data of the path points, compares the pollutant diffusion rate of the path points according to the pollutant concentration change value and water flow velocity data, screens out the path points where the diffusion rate exceeds the diffusion rate threshold, and establishes a pollutant diffusion trend evaluation result according to the number of screened path points and the flow direction azimuth parameter; The warning level determination module, based on the pollutant diffusion trend evaluation result, acquires the pollutant diffusion path data and permeability characteristic data of the corresponding path points, compares the pollutant diffusion path data and permeability characteristic data one by one, screens out the path points where the permeability characteristic parameter exceeds the diffusion risk threshold, and performs weighted calculation according to the number of screened path points and the pollutant diffusion trend evaluation result to obtain a pollution diffusion warning level result.

Images